9984b730e8070704466d394c09272b8a

This model is a fine-tuned version of albert/albert-xxlarge-v2 on the nyu-mll/glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.5860
• Data Size: 1.0
• Epoch Runtime: 17.2628
• Accuracy: 0.8086
• F1 Macro: 0.7769
• Rouge1: 0.8096
• Rouge2: 0.0
• Rougel: 0.8086
• Rougelsum: 0.8086

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.6812	0	1.0866	0.6377	0.5163	0.6377	0.0	0.6377	0.6387
No log	1	267	0.6836	0.0078	1.7720	0.5205	0.4498	0.5205	0.0	0.5205	0.5205
No log	2	534	0.6158	0.0156	1.7797	0.6885	0.4108	0.6895	0.0	0.6885	0.6885
No log	3	801	0.6296	0.0312	2.1033	0.6611	0.6026	0.6611	0.0	0.6611	0.6616
No log	4	1068	0.5519	0.0625	2.4921	0.7021	0.4733	0.7031	0.0	0.7031	0.7012
0.0336	5	1335	0.6704	0.125	3.4358	0.7236	0.5739	0.7236	0.0	0.7236	0.7231
0.4919	6	1602	0.4829	0.25	5.3458	0.7871	0.7350	0.7861	0.0	0.7861	0.7871
0.4105	7	1869	0.4351	0.5	9.3113	0.8174	0.7753	0.8174	0.0	0.8174	0.8174
0.3572	8.0	2136	0.4500	1.0	17.4779	0.8164	0.7780	0.8164	0.0	0.8164	0.8164
0.2837	9.0	2403	0.4056	1.0	17.1662	0.8320	0.7872	0.8320	0.0	0.8320	0.8320
0.2434	10.0	2670	0.4391	1.0	17.1180	0.8320	0.7996	0.8320	0.0	0.8320	0.8320
0.1855	11.0	2937	0.4628	1.0	17.0875	0.8232	0.7965	0.8232	0.0	0.8232	0.8223
0.1922	12.0	3204	0.5114	1.0	17.1420	0.8057	0.7759	0.8057	0.0	0.8047	0.8066
0.1294	13.0	3471	0.5860	1.0	17.2628	0.8086	0.7769	0.8096	0.0	0.8086	0.8086

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1